Automate Audio Transcription & Summary with n8n, Google Drive & OpenAI

What This Automation Does

This workflow watches a Google Drive folder for new audio files.
When a new file appears, it downloads the file, changes speech in the audio to text using OpenAI Whisper, and then summarizes that text with OpenAI GPT-4 Turbo.
After that, it makes a new page in Notion with the summary.
This saves time by doing transcription and notes automatically and keeps the team updated fast.

Who Should Use This Workflow

This is good for people who work with many audio recordings.
If the user must transcribe and write key points often, this saves many hours per week.
It helps podcast producers, journalists, content creators, and others who want less manual work and more accurate notes.

Tools and Services Used

• Google Drive: Triggers when new audio file is added and stores files.
• OpenAI Whisper: Transcribes speech in audio to plain text.
• OpenAI GPT-4 Turbo: Creates a structured JSON summary from the transcript.
• Notion API: Makes new pages with summary content for teams.
• n8n: Connects all steps into one automated workflow.

How This Workflow Works (Input → Process → Output)

Inputs

• A new audio file uploaded to a specific Google Drive folder.

Processing Steps

• File Detection: Google Drive Trigger node notices new files every minute.
• File Download: Google Drive node downloads the audio’s binary data.
• Speech to Text: OpenAI Whisper node transcribes audio to plain text.
• Text Summarization: OpenAI GPT-4 Turbo node creates detailed JSON summary including title and key points.
• Summary Storage: Notion node creates a new page with the summary content.

Output

• A new Notion page with transcription and rich summary ready for team use.

Beginner Step-by-Step: How to Use This Workflow in n8n

Step 1: Import the Workflow

1. Download the workflow file using the “Download” button on this page.
2. Open the n8n editor.
3. Click “Import from File” and select the downloaded file.

Step 2: Configure Credentials

1. Add required API Keys and OAuth2 credentials for Google Drive, OpenAI, and Notion.
2. Make sure credentials have permissions to read/write where needed.

Step 3: Update IDs and Settings

1. Edit the Google Drive Trigger node to use the correct folder ID for your audio files.
2. Update the Notion node with the correct parent Page ID where pages will be created.
3. If needed, adjust email, Slack channels, or other fields in added nodes.

Step 4: Test the Workflow

1. Upload a sample audio file to the configured Google Drive folder.
2. Manually run the workflow or wait for it to trigger.
3. Check if transcription and summary are created and saved to Notion.

Step 5: Activate Workflow for Production

1. Enable the workflow by toggling the active switch in n8n.
2. Monitor first several runs to catch errors.

If you plan to self host n8n, visit self-host n8n for more info.

Important Configuration Details

The Google Drive Trigger node must watch the folder where audio files get uploaded.

The OpenAI Whisper node must receive the audio binary property correctly for transcription.

The GPT-4 Turbo node uses a long system prompt to produce JSON summaries.

{
"system": "Extract title, summary, key points, actions with dates, stories, references, arguments, themes, sentiment from the transcript text in JSON format.",
"user": "Transcript text here"
}

Notion node uses JSON expressions to set page title:

{{JSON.parse($json["message"].content).audioContentSummary.title}}

Customization Ideas

• Change how often Google Drive Trigger checks for new files.
• Edit the OpenAI summarization prompt to fit your need.
• Add Slack or email nodes to notify the team after summary creation.
• Include more metadata or tags in Notion pages for sorting.
• Add error nodes to handle transcription or API failures.

Edge Cases and Troubleshooting

Problem: Workflow does not start on new Google Drive files.

Cause: Wrong folder ID, or permissions missing.

Solution: Double check folder ID and OAuth2 credentials.

Problem: OpenAI Whisper node returns error or no text.

Cause: Binary audio not passed or unsupported file type.

Solution: Make sure audio is mp3 or wav and correct binary is linked.

Problem: Notion page creation fails with permission or ID errors.

Cause: Notion API token not authorized or wrong page ID.

Solution: Confirm Notion API integration and Page ID.

Pre-Production Checklist

• Confirm Google Drive OAuth2 connection works with access to the folder.
• Upload a test audio file to trigger workflow.
• Verify OpenAI API keys are valid for Whisper and GPT-4 Turbo.
• Check Notion API integration can create pages.
• Review all JSON paths and expressions for correct data mapping.

Deployment Guide

Activate the workflow by turning on the active switch inside n8n.

Watch initial workflow runs for possible errors or issues.

Add notification nodes if you want alerts on errors or completions.

Be aware of API usage limits and split workflows if many files come in at once.

Summary & Results

✓ Saves many hours of manual transcription and note writing.

✓ Improves accuracy of transcripts and summaries by using AI.

✓ Creates structured notes in Notion for better team collaboration.

→ Quickly processes new audio files without manual steps.

→ Enables focus on creative work instead of repetitive tasks.